Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.5254. Min Act: -0.1700
Data Index: 5684199 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.4942. Min Act: -0.1700
Data Index: 1074854 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.4629. Min Act: -0.1700
Data Index: 7136806 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.4004. Min Act: -0.1700
Data Index: 5684201 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.4317. Min Act: -0.1700
Data Index: 242487 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.4004. Min Act: -0.1700
Data Index: 5684203 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.3379. Min Act: -0.1700
Data Index: 5684200 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.3379. Min Act: -0.1700
Data Index: 2330279 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.3692. Min Act: -0.1700
Data Index: 4292584 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.2754. Min Act: -0.1700
Data Index: 5560775 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.2754. Min Act: -0.1700
Data Index: 2877586 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.2442. Min Act: -0.1700
Data Index: 8098305 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.2129. Min Act: -0.1700
Data Index: 5684202 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.2129. Min Act: -0.1700
Data Index: 4549137 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.1504. Min Act: -0.1700
Data Index: 1964793 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.1504. Min Act: -0.1700
Data Index: 2705069 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.0879. Min Act: -0.1700
Data Index: 4125731 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.1192. Min Act: -0.1700
Data Index: 1806756 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.1192. Min Act: -0.1700
Data Index: 5072914 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5254. Min Range: -7.5254
Max Act: 7.0567. Min Act: -0.1700
Data Index: 8082477 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19